© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76891
    Prev
    Next
    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andas
    0.51
    ück
    0.43
     purify
    0.42
     ü
    0.40
    ání
    0.40
     castes
    0.40
    ci
    0.39
    ık
    0.39
     ప్రే
    0.39
    elas
    0.38
    POSITIVE LOGITS
    われる
    0.49
    हीं
    0.48
    س
    0.47
     semelhante
    0.44
    稱
    0.44
    inek
    0.44
     inflicted
    0.44
     knj
    0.44
    <0x85>
    0.43
     স্যাম
    0.43
    Activations Density 0.001%

    No Known Activations